A pixel-level dataset of 547 earthquake images is introduced, and a fine-tuned SegFormer plus a depth-adjusted scoring equation produces damage scores that rise with labeled severity.
Damage assessment from social media imagery data during disasters
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
From Pixels to Damage Severity: Estimating Earthquake Impacts Using Semantic Segmentation of Social Media Images
A pixel-level dataset of 547 earthquake images is introduced, and a fine-tuned SegFormer plus a depth-adjusted scoring equation produces damage scores that rise with labeled severity.